Large Language Model Agents

Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly. We formalize this threat as adaptive transcript privacy and introduce DP-MemView, a differentially private interface that privately selects public response-conditioning views and exposes those views---rather than raw memory---to the response LLM. Each private selection is charged to every protected attribute whose memory group intersects the read set. Per-attribute ledgers block any selection that would exceed its cap and return a fixed generic view instead. Under an explicit interface contract, we prove pure B_a-DP for the entire adaptive transcript. We also extend the result to stores that differ across multiple protected groups and bound how much observing the transcript can change an adversary's prior odds. We evaluate the online and preallocated modes with three response LLMs on a controlled adjacent-store benchmark and a public-corpus transfer track. Both modes keep transcript distinguishability near chance while preserving target-required personalization and overall response quality. Further diagnostics show that removing key safeguards causes mismatched output support, missing ledger charges, revealing side channels, or growing long-horizon leakage.

Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool and orchestrating the order of calls. However, correctly filling the parameters of a tool call is equally critical for successful execution and has received far less attention. In domains such as cloud networking, even frontier models correctly complete fewer than half of tool calls. Inspired by recent analyses showing that LLM hidden states encode rich information about model predictions, we discover that while the model generates a parameter value, its hidden state contains a strong correctness signal: a simple linear probe can accurately predict whether the value will be correct. Based on this observation, we propose a unified probe-guided framework with two complementary approaches: probe-filtered bootstrapped training (PBT), which uses the probe to filter reliable self-generated calls for fine-tuning, and probe-guided reranking (PGR), which uses the probe to select better candidates during inference. To support systematic evaluation, we release ParamBench, a benchmark built from real cloud-network APIs that categorizes every instance into five difficulty levels according to parameter nesting depth, cross-parameter dependencies, and the reasoning required to derive values from earlier calls. Extensive experiments across 5 open models on ParamBench and 6 external benchmarks demonstrate that our method substantially improves parameter generation, raising the average exact match from 19.7% to 59.6%.

LLM-based multi-agent systems are increasingly used to simulate social dynamics, from opinion formation to collective decision-making. These simulations can reproduce certain social phenomena, but it is unknown whether they capture pluralistic ignorance, a state where a majority privately rejects a norm yet publicly conforms, each believing they are alone in dissenting. This phenomenon drives norm persistence, social movements, and political revolutions. We show that pluralistic ignorance emerges robustly in LLM agent populations. We construct a benchmark of 100 scenarios across 10 domains and 5 authority levels, grounded in the human pluralistic ignorance literature, and evaluate 8 models from 6 organizations. Agents publicly conform at rates of 64 to 94% despite privately opposing the norm. Conformity is domain-sensitive (workplace and social relationship scenarios produce near-universal compliance) and highly model-dependent, though uncorrelated with capability. We test whether a single "norm entrepreneur" can break the false consensus by publicly dissenting. For 7 of 8 models, cascades succeed less than 26% of the time, with one model showing zero cascades across all scenarios. GPT-4o is a notable outlier at 48%, revealing qualitatively distinct dynamics across model families. A prompt component ablation across all 8 models establishes that conformity is emergent rather than instruction-driven: removing both the false-consensus framing and fit-in goal reduces conformity but does not eliminate it (52 to 92% in the minimal condition). Our findings identify model selection as an unacknowledged degree of freedom that fundamentally shapes simulation outcomes. More broadly, the near-absence of cascades suggests LLM simulations may systematically overestimate the stability of social norms, missing the fragile tipping-point dynamics that drive real-world norm change in human societies.

Large language model agents increasingly solve complex tasks by composing reusable skills from a library. To address this, the key challenge is not merely to retrieve individually relevant skills, but to identify a complete and executable skill composition. In this paper, we argue that this problem can be solved in a graph with three levels: compositional relations among skill queries, similarity between queries and candidates in the skill library, and the dependencies among the selected candidates. We introduce SkillTrace, which organizes the user query into a semantic hierarchy, matches skill queries and candidates, and propagates over the skill dependencies. Experiments on SkillsBench and ALFWorld demonstrate that SkillTrace achieves state-of-the-art performance, reaching a success rate of 53.17% on SkillsBench and 91.43% on ALFWorld. SkillTrace also delivers consistent improvements across different backbone language models, demonstrating the generality and robustness of graph-based skill retrieval.

Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation (OPSD) provides dense token-level supervision from a privileged teacher, but the teacher may not be reliable at every position. Existing methods commonly rely on isolated token-level discrepancies, which can be sensitive to noise, or assign a shared step-level weight that may overlook positional variation. We propose Persistent Consistency Self-Distillation (PCSD), which derives token-level distillation weights from the local persistence of teacher-favoring signals. PCSD combines adaptive windows with exponentially decayed aggregation to capture persistent relative teacher support, applies trend-aware modulation to attenuate locally declining support, and produces continuous weights through sigmoid gating. The resulting objective is jointly optimized with GRPO, combining dense teacher guidance with sparse environmental feedback. Without inference-time skills, PCSD achieves the best ALFWorld Overall results among all baselines on both backbones, exceeding GRPO by 15.6 and 13.3 points and SDAR by 6.2 and 5.5 points, while remaining competitive on WebShop and gaining 15.8 points over GRPO on unseen ALFWorld split.

LLM agents increasingly run policy-bound enterprise workflows such as document auditing, where they must apply rules consistently, ground every value, and stay auditable. Improving these agents is hard: operational feedback is sparse and unlabeled, edits to one rule can regress unrelated cases, and accuracy must improve without inflating inference cost or losing auditability. We present FRAMES, a closed-loop framework that cold-starts deployable skills from existing assets and then evolves them through consensus-based mutation, Pareto selection over accuracy and cost, and an anti-regression guarantee, all while preserving auditability. Deployed on our internal production system, FRAMES attains the best accuracy-cost trade-off among baselines, with the same gains reproduced on tau-bench.

Long-term memory is critical for LLM agents operating over long-horizon interactions. However, several persistent limitations of existing memory systems can be traced to two recurring misalignment patterns in long-term interaction settings: Temporal-Structural Misalignment (TSM) and Delayed Utility Manifestation (DUM). TSM arises when temporal proximity does not reliably align with topical or event-level relatedness, whereas DUM arises when write-time salience does not reliably predict future query utility. To mitigate these misalignment patterns, we propose MemSIF (Memory with Structured Interactions and Facts), a structured interaction-to-fact memory framework. Structured Interaction Memory organizes raw interactions into Topical Segments that preserve local topical coherence and Event Trajectories that maintain cross-time event continuity. Dual-Track Fact Memory uses two complementary tracks: CoreFact memory consolidates stable, schema-guided information at write time, whereas ActiveFact memory forms facts on demand and promotes those supported by multiple historical sources and recurring query demand for reuse. Experiments on LoCoMo and LongMemEval-S across five backbone LLMs show that MemSIF achieves the highest Total ACC in all settings, outperforming the strongest baseline by 2.29%-8.79% on LoCoMo and 2.87%-6.15% on LongMemEval-S. These results support the effectiveness of combining Structured Interaction Memory with Dual-Track Fact Memory to mitigate TSM and DUM. Code is available at https://github.com/luoyufeihaha/MemSIF.

As memories accumulate across tasks and sessions, the performance of long-term LLM agents depends jointly on query-specific retrieval and continual memory refinement. However, existing methods typically optimize either memory access, through iterative query refinement or adaptive retrieval policies, or memory evolution such as structural update. This separation overlooks a fundamental feedback loop: retrieval determines which memories receive usage signals, while updated memory bank reshape future retrieval. We propose \textbf{CoEvo-Mem}, a closed-loop framework for co-evolving the retrieval policy and memory bank. For each query, a frozen LLM generates route-specific query rewrites and a routing prior, which a lightweight residual router corrects online. The retrieved context serves as the coupling interface between the two learning processes: task outcomes assign credit to routing decisions, while trajectory-conditioned feedback updates memory values and graph relations. These updates alter how memories are ranked and selected for subsequent queries, thereby closing the feedback loop. To mitigate coupling induced non-stationarity, CoEvo-Mem alternates between updating the router with the memory bank fixed and evolving the memory bank with the retrieval policy fixed. Across seven diverse benchmarks, \textbf{CoEvo-Mem} achieves state-of-the-art performance, demonstrating the importance of retrieval-memory coevolution.

Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate graph analysis as text-based question answering, where graph information is directly provided in the prompt, limiting the evaluation of end-to-end agentic capabilities. To address these limitations, we introduce GABench, a comprehensive benchmark for agentic graph analysis. GABench spans three graph types and covers four graph analysis task categories: graph retrieval, graph theory, graph machine learning, and graph open-ended question answering. GABench also provides 84 executable tools for accessing graph data and performing diverse graph operations. Building on these tools, we develop an agentic graph analysis task generation pipeline and construct 10,400 tasks with verifiable ground truth.Using GABench, we evaluate a range of frontier LLMs and agent harnesses. Our experiments reveal three key findings: (1) Existing LLM agents still struggle with complex graph analysis tasks. (2) Harness choice significantly affects performance, yet existing harnesses remain limited on complex graph tasks. (3) Graph analysis depends more on tool-call quality than quantity. Our findings provide practical insights into the development and evaluation of LLM agents for graph analysis.

Long-term memory enables LLM agents to retain useful information across sessions, but also creates an attack surface through which adversaries may poison an agent's persistent memory to steer its behavior. Existing memory poisoning attacks mainly rely on individually malicious records, overlooking a compositional threat: multiple benign-looking memories may jointly induce unsafe behavior. In this paper, we introduce MemCollusion, an automated red-teaming framework for constructing collusive memory poisoning attacks. MemCollusion applies salami tactics---a strategy that slices an adversarial objective into small, individually innocuous pieces---to generate memory fragments that are individually benign looking but collectively harmful. It constructs memory coalitions using four design constraints, five theory-informed strategies, and a fine-tuned generator. To assess collusive memory poisoning in a realistic cross-session setting, we develop MoltLab, a controlled research reproduction of Moltbook, in which crafted platform content must first be observed and distilled into persistent memory before influencing the agent's behavior in a separate session. We evaluate MemCollusion on OpenClaw using two backbone models across 48 scenarios. Under the strongest memory-saving setting, MemCollusion achieves an average Memory Save Rate of 81.3% and an Attack Success Rate of 75.0%, and remains effective under both benign memory dilution and memory-level defenses.

Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups. We present TraceCompiler, a skill-guided system that mines clusters of noisy agent traces and compiles them into executable, mostly deterministic workflows. It admits an inter-tool dependency only when a consumer argument contains a value attributable uniquely to an earlier producer; every hard edge carries an auditable evidence tuple, and ambiguous relations are marked suspected and impose no ordering constraint. Bindings are classified as constants, user inputs, copied outputs, transforms, or residual LLM decisions. On T1, a mechanized form of the rule recovers producer-consumer dependencies at 0.928 precision and 0.943 recall over 15,775 def-use edges of its training split, against 0.711 F1 for adjacency and 0.712 for a frequency-thresholded directly-follows measure on identical data; the compiler skill run blind reaches 0.992 on 250 of those edges. On AppWorld we replay released trajectories in the deterministic simulator to recover masked return values and measure the rule against 563 token edges at 0.993 precision - a self-consistency check, since replay injects tokens by a related heuristic. We compile two recurring intents: a Venmo money-request intent reduces 34 observed API calls to 11 runtime calls and, under leave-one-out execution against the benchmark's own state tests, passes 15 of 21, the failing fold escalating rather than acting because its required branch was never observed; and a Spotify/Todoist intent the compiler correctly refuses to compile, because an irreversible side effect is under-determined. We measure call reduction but not offline compilation cost, so we claim no net efficiency result.

Constructing an executable chemical-process model remains manually intensive. Chemical engineers translate underspecified requests into coupled decisions about unit operations, thermodynamics, streams, specifications, degrees of freedom (DoF), initialization, solver repair, and optimization; one error can invalidate the model. CRAFTS mirrors the staged workflow of chemical engineers by decomposing simulation building into bounded subtasks assigned to seven bounded roles, with deterministic IDAES/Pyomo gates between stages. Given a natural-language request, process flowsheet diagram (PFD) evidence, and curated chemical-engineering knowledge, Input Understanding and Intent recover requirements, constraints, and process semantics; visual, topology, and specification specialists translate them into typed simulator contracts; and Debug and Optimization support bounded repair and eligible optimization. Fine-tuning is applied to the three schema-critical visual, topology, and specification roles, while the remaining roles use untuned Qwen. The resulting VisualGraphIR, TopologyIR, SpecIR, BuildPlan, and SolveReport expose unit, port, thermodynamic, numerical, and execution decisions. Compatible constructors, property packages, and runners are attached only after semantic artifacts pass engineering gates. We introduce OpenIDAES-450, a 450-case IDAES process- simulation dataset, and evaluate the complete seven-role LangChain/LangGraph workflow through solve and eligible optimization on its frozen 82-case held-out split. CRAFTS completes the prescribed validation and execution contract for for 91.5% of cases and achieves unit, stream, and directed-connection F1 scores of 0.815, 0.791, and 0.782. These results demonstrate the effectiveness of role specialization, typed intermediate representations, and deterministic engineering gates for reliable automated process-model construction.

The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interactions. Existing memory systems either compress and structure histories for efficient access or perform deep research over broader trajectories. The former lowers online cost but may omit temporal, causal, or cross-step dependencies, while the latter improves evidence coverage at substantial latency and inference cost. This raises a key question: can a memory system achieve strong answer quality while maintaining low online latency? We introduce Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory. Router-Mem first applies a shared low-cost retrieval prefix to obtain evidence. A lightweight sufficiency router then predicts whether the context supports early termination, which enable a single-token decision at inference time. It is trained with evidence-level supervision and rationale-conditioned representation distillation. When evidence is insufficient, Router-Mem reuses retrieval hits to expand memory blocks and perform deeper analysis and aggregation. Experiments on AMA-Bench and BEAM show that Router-Mem achieves 55.17% and 38.77% score while reducing average inference time by 27.3% and 25.5% compared with full memory execution.

Large language model agents increasingly operate in dynamic environments where tool interfaces, APIs, and user requirements change after deployment. Existing self-evolution methods mainly follow two paradigms: harness-based approaches, which externalize feedback into editable memories or skills for rapid adaptation, and parameter-based approaches, which internalize experience into model parameters for deeper capability improvement. However, using either mechanism alone creates a trade-off between flexibility and performance. This paper asks how an agent can coordinate both channels to achieve robust self-evolution. We present COVE, a unified agent self-evolution framework that combines harness-based and parameter-based learning through task-aware routing, stage-aware scheduling, and knowledge optimization. Through this design, COVE treats self-evolution not as indiscriminate accumulation of experience, but as a coordinated process that matches tasks and knowledge types to appropriate learning mechanisms. Experiments across multiple task categories show that COVE outperforms single-channel evolution strategies, demonstrating more robust and efficient improvement under changing environments.

Production LLM agents that select from large skill libraries face a limitation that semantic relevance alone cannot resolve: a skill may match a user's topic yet be impossible to execute in the current account state. We present a deployed three-stage selection pipeline for Helpmate, Wix's customer-care assistant. First, a recall-oriented semantic matcher identifies messages related to a ten-skill domain family without consulting account state. Second, a deterministic executability gate removes candidates whose internal hard-stop conditions hold. Because the gate and the skill evaluate the same exit predicates, every blocked candidate would be unable to complete under the same account state, provided predicate parity is preserved and both checks observe fresh authoritative state. Finally, the LLM decides whether to invoke one of the remaining candidates. In a post-launch production analysis of 756.6K user messages across 267.6K conversations, semantic matching retained 174,927 messages (23.1%). Within this matched stream, the gate removed 1,039,462 of 1,749,270 skill-message pairs (59.4%), saving 228.8 million skill-description tokens -- 59.1% of the post-semantic skill-description footprint. Together, semantic matching and executability gating reduced skill-description context by 90.5% relative to exposing all ten skills to every message. To test whether this pruning affects model behavior rather than context size alone, we replayed a risk-enriched cohort of 1,000 conversations with all ten skills exposed. The model selected a production-blocked skill in 78 conversations (7.8%). This counterfactual result shows that deterministic gating prevents non-executable candidates from influencing model selection, while not claiming downstream tool execution or customer-outcome effects.

LLM agents accumulate long trajectories of reasoning steps, tool calls, and environment feedback, making the KV cache a major inference bottleneck. KV cache compaction can reduce this cost, but most prior methods assume a static context where future queries are known or can be approximated offline. Agents instead require online compaction: new information must be compressed before future relevance is known, using proxy queries cheap enough for the inference path. We study online compaction across token eviction (TE) and attention matching (AM), adapting both to compact agent turns and comparing cheap proxy sources such as boundary, repeat-prefill, and delayed future-generation queries. Experiments on BrowseComp-Plus and WideSearch show that immediate compaction often hurts performance, whereas delaying compaction to use the agent's future queries recovers much of the gap. Moreover, TE is often more robust than AM under imperfect proxies. Across models at different scales, TE preserves most of the accuracy while reducing KV cache by 80%, and can improve throughput over the no compaction baseline. These results position proxy-query selection as a core design choice for practical online KV compaction.

Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields including AI for mathematics. We study this setting through weighted sum-of-squares (SOS) decomposition, a machine-checkable route to proving polynomial nonnegativity and hence polynomial inequalities. A candidate decomposition can be checked exactly, but finding one requires choosing among non-unique regroupings and coordinating multiple symbolic transformations. We develop an agent that combines algebraic task training, symbolic tools, and verifier-grounded optimization for this task. Rather than training only on the composite SOS task, we construct 1.35 million synthetic examples covering eight supporting polynomial tasks together with weighted-SOS decomposition. We first apply supervised fine-tuning (SFT) to direct algebra problems and simulated symbolic traces, and then use Group Relative Policy Optimization (GRPO) with task-specific symbolic rewards. The SFT corpus contains no native tool-calling messages; at evaluation, the agent uses native SymPy calls for expansion, collection, reordering, and factorization. Every final SOS answer is checked by exact expansion and coefficient comparison. On held-out, same-generator synthetic problems, the full SFT+GRPO+tools system is the strongest of four evaluated configurations, reaching 78.96% verified success on weighted SOS, compared with 44.73% for the base model with the same tools, and 91.75% macro accuracy across nine polynomial tasks. Within this controlled setting, our work provides a case study of combining domain-specific skill training, executable tools, and verifier feedback, and may inform the design of tool-calling agents in other domains with exactly checkable outputs.

Memory for self-evolving large language model (LLM) agents is often provisioned as if its byte budget only grows. Cloud platforms, however, adjust quotas with load and cost, and we show that capability does not follow the budget back up: after a squeeze-and-recover cycle, the agent settles below its pre-squeeze level, a gap we call memory hysteresis. The cause is structural. Deletion and one-way compression discard the material needed for later rebuilding, and we prove that any policy that only keeps or drops entries carries a residual-deficit floor. We propose CrystalMem (Crystallized Memory), an elastic memory sidecar that demotes entries across four fidelity states under a crystallization-energy schedule, orders demotions by advantage-weighted influence with dependency coupling, and recovers capability through verified recrystallization under explicit compute and byte caps. Across seven environments, seventeen methods, and six backbones, with multi-tenant serving and a physical edge-cloud deployment, CrystalMem achieves the highest restored capability in every setting and closes the loop left open by every baseline. From a 50% byte budget, CrystalMem matches the strongest budgeted baseline at full provision on every environment; at equal budgets, it leads by +4.6 pp on average.

Large language model (LLM) agents can retrieve memory, call tools, ask clarifying questions, and vary response style, yet adapting these execution decisions to an individual user remains difficult. Fine-tuning a separate LLM is costly or impossible for proprietary systems, while prompts and memory primarily expose user information to the agent rather than adapt its execution decisions from feedback. We formulate personalization of a frozen agent as online learning of a per-user execution policy from scalar feedback observed only for the executed action. We propose FABLE (Factorized Adaptive Bandit Layer for Execution), a lightweight policy layer outside a potentially black-box host agent. FABLE factorizes memory, information-acquisition, and response decisions so feedback updates related choices; filters actions through an externally specified feasible set before exploration; and learns user-specific residual preferences relative to a fixed default-and-cost score via Bayesian contextual Thompson sampling. Under a linear residual-reward model, a calibrated variant inherits an expected-regret bound against the best feasible action. We also characterize preferences unidentifiable under persistent feasibility constraints and provide anytime-valid false-promotion control. Across personalized-reasoning, controlled-feedback, and executable tool-use evaluations, FABLE improves several preference-sensitive behaviors relative to rule-only control while remaining competitive on end-to-end task performance.

Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \texttt{Isolated}, \texttt{Sequential}, and \texttt{Interleaved} streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-evolution. Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving agents should be evaluated under realistic task streams rather than isolated single-task settings.

Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (schema-conforming feature extraction, non-crashing A/B, zero compliance-path hallucination), and end-to-end efficiency. Any two can be maximized against the third. We present RecSys Factory, an LLM-agent platform deployed for 78 days across three heterogeneous Tencent recommender business lines. The design principle is autonomy at decision points, not over pipelines, made concrete through three deconstructions that each discharge one vertex of the trilemma. Runtime is deconstructed into three host-emitted event sources (Claude Code Stop hooks, corporate-IM webhooks, workflow scheduler APIs): the platform carries no long-running daemon during the wait phase and consumes zero CPU during the 94% of wall-clock spent waiting on Spark or GPU jobs. Capability is deconstructed into a 29-file skill ecosystem (8,971 lines of SKILL.md) whose per-skill pitfall tables mechanically compile into a 400-entry PitfallStore, confining autonomy to bounded typed decision surfaces inside pre-committed pipelines. Deployment spans three business lines with disjoint label semantics, A/B layer topologies, and operator personas; an onboarding-time compression is observed on two of the three and is reported as a case-study observation, not a generalization claim, and not measured against a controlled pre-platform baseline. The human is retained at the diagnostic-versus-execution boundary via a human-in-the-loop card protocol, deployed as an audit-trail primitive (schema-validated, idempotent, replayable) and reported from an 8-day 16-run pilot. Across the 78-day window the platform recorded 1,624 CLI-tool dispatches at a 78.6% aggregate success rate.

Tool-using LLM agents act on typed tool returns, records pairing provenance and categorical fields with numerical values. Runtime permission gates generally authorize the observed return and action, leaving the decision unprotected against small errors in how the return was bound to its source. We ask whether a candidate action stays authorized over a declared neighborhood of plausible correctly bound returns: one admissible binding fault plus bounded numerical drift. We prove that certifying the categorical and numerical channels separately does not compose: perturbations that are safe on each channel alone can jointly turn the same action unsafe. CAGE certifies this joint neighborhood directly, enumerating the discrete branches exactly and certifying the continuous perturbation within each branch. Across synthetic, policy-as-code, regulatory, and real-transaction settings, CAGE removes the in-budget false allows that accurate pointwise gates admit, while keeping a useful fraction of decisions autonomous. When the policy is executable, CAGE-Exact certifies the policy itself; otherwise CAGE-Lip and CAGE-RS certify a learned gate under an explicit, measured fidelity assumption.

Long-term memory lets large language model(LLM) agents reuse prior preferences and work flows, but it also turns untrusted observations into persistent action context. We identify memory provenance laundering: during LLM-based memory consolidation, an external observation may be rewritten as apparent user history or workflow support, preserving an action trigger while erasing the low-trust source that should limit its authority. Existing prompt filters, content sanitizers, and tool guards do not enforce source-authority non-amplification after lossy memory consolidation. We formalize this boundary and instantiate it as Provenance-Preserving Memory Fire wall (PPMF), a lightweight memory middleware that preserves platform-maintained provenance and authorizes tool calls by matching action risk to the authority of action-relevant memories. In our schema-grounded evaluation with fixed risk policies, vulnerable consolidated memories reach up to 1.000 attack success rate(ASR); with intact platform-maintained provenance, confirmation, and risk labels, no evaluated unauthorized high-risk action passes the PPMF gate while confirmed benign actions and targeted low-risk memory use remain executable.

Large language model (LLM) agents increasingly operate over long interaction histories, where effective reasoning requires identifying and exploiting task-relevant evidence distributed across past observations and actions. However, useful information encoded in previously computed representations is often underutilized during subsequent generation. We propose \textbf{TransMem}, a lightweight inference-time parametric memory module that transforms sparse historical hidden states from a frozen LLM backbone into reusable memory representations. TransMem uses a lightweight gating network to dynamically apply the latent intervention to the current hidden states, without repeatedly encoding the preceding context. To learn transferable memory utilization rather than task-specific knowledge, we introduce evidence-conditioned self-distillation. A memory-augmented student processes the full context and matches the predictive distribution of an evidence-only teacher that shares the same frozen backbone. Experiments on LoCoMo, HotpotQA, and MemoryAgentBench demonstrate consistent improvements across different model architectures and scales. TransMem yields gains of 11.58--29.25 $F_1$ on LoCoMo and 10.20--13.03 $F_1$ on HotpotQA, while improving the average MemoryAgentBench accuracy from 29.54% to 40.00%. These results establish sparse historical hidden states as an effective and efficient memory substrate for long-context LLM agents. Our code is available at https://github.com/Haodong-Lei-Ray/TransMem.

Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim. Long-horizon scientific analysis remains constrained by the lack of process supervised environments over real-world scientific data. This paper introduces SciDisco, a scalable framework for training Scientific Discovery agents in process-verifiable environments. SciThèque compiles hypotheses, datasets, hidden evidence graphs, and verifiers into task environments where analytical progress can be checked during interaction. DAG-grounded trajectory synthesis uses these environments to construct verifier-filtered multi-turn demonstrations. DiscoPO then uses the environment as the source of training signal, assigning turn-level credit to actions that produce verifiable analytical evidence. Experiments show that SciDisco-14B reaches state-of-the-art on hypothesis-driven scientific data analysis benchmarks.

Evaluating LLM coding agents in algorithmic trading is difficult because static benchmarks risk data contamination and numerical backtest outputs require ground truth from actual code execution. We present Backtrader-Bench, a framework with two complementary pipelines. A deterministic multiple-choice question (MCQ) pipeline generates questions from backtest configurations across five trading strategies, 33 templates, and three difficulty tiers, with an independent checker that re-derives every answer. A generator-solver filtering pipeline autonomously mines harder questions: a generator writes questions verified by executable code, converts them to MCQs, and discards any that a no-tool solver can answer without code execution. We evaluate 11 models without tools (10 runs each) and four with-tools configurations on a 30-question curated set. Tool-augmented agents reach 90.0% accuracy in a single pass (GPT-5.5 and Opus 4.7), outperforming the best no-tools baselines (73.0%, averaged over 10 runs) by 17 percentage points. On 38 separately mined questions, no-tools accuracy drops further, with half the models falling to roughly random-chance level (25%). Beyond evaluation, the scalable MCQ infrastructure is designed to produce a training corpus for reinforcement learning, with the ultimate goal of building a specialized agent for quantitative trading workflows.

Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across extended horizons while adapting decisions to accumulated evidence. Evaluating this capacity requires a persistent environment in which actions constrain future choices, feedback arrives at heterogeneous delays, and incoherent behavior produces measurable cumulative effects. Seller-side e-commerce provides a suitable setting for this evaluation through recurrent and interdependent decisions over Product Sourcing, Listing and Pricing Control, Cash-Flow Management, and Mixed-Latency Feedback Adaptation. We introduce MerchantBench, a 365-day order-level simulation grounded in 98,843 real e-commerce product records and equipped with 26 tools for agent interaction. MerchantBench couples promptly observable Upstream Supplier Events with delayed Downstream Order Outcomes, requiring agents to follow individual order lifecycles and revisit earlier decisions. We evaluate eight LLMs under two agent frameworks in 48 runs, each spanning 365 simulated days. Our results reveal a substantial gap between even the latest LLMs and human participants, with the best LLM configuration attaining only 27.3% of the mean final net assets achieved by human participants.

Recently Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and scientific discovery. In these settings, agents must act based on limited observations rather than full environmental states, leading to partial observability. This introduces several key challenges: belief state inference, task objective misalignment, and planning under uncertainty. Prior approaches typically condition actions on full or summarized action-observation histories whose redundant and irrelevant information can mislead the decision making of LLM agent. Inspired by human cognition, we propose a novel neuro-symbolic fast-slow thinking (NeSyFS) framework for LLM agent, addressing the challenges introduced by partial observability in a unified approach. We use a knowledge graph (KG) to represent the belief state, providing triplets as context for every module of NeSyFS. The fast-thinking module performs reactive action, while slow-thinking conducts a new uncertainty-aware planning by following the high-level structure of twisted sequential Monte Carlo (TSMC) algorithm. To mitigate the misalignment of task objective, a reflection module is used to reflect fast-thinking actions, and also switches to the slow-thinking module whenever reactive actions repeatedly fail. Experiments on three representative benchmarks, i.e. ALFWorld, Webshop, and ScienceWorld, demonstrate significant advantages over previous methods.

A single human must audit $N$ LLM agents under a budget of $B \ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy inspection over a two-level Gaussian copula and locate the miscalibration threshold $δ^*$ past which confidence-ranked auditing is \emph{worse} than random. Two a-priori expectations reverse: $δ^*$ \emph{rises} as the budget shrinks, and cross-family correlation is not low---shared difficulty dominates lineage. Five open-weight LLMs show operationally useless (near-constant) confidence, point estimates at or beyond the flip though CIs straddle it; a proprietary model is informative and lands below it. We give a quantitative criterion for \emph{vacuous} oversight, and replaying policies on recorded traces confirms the ordering.

Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the agent's current situation. This ``replay'' paradigm ignores the gap between the abstract, general nature of stored experience and the concrete, ever-changing states encountered at decision time, frequently causing negative transfer. In contrast, humans rarely recall past experiences verbatim; instead, they reorganize and adapt retrieved memories to fit the present context. Inspired by this, we propose MemHarness, a framework that equips LLM agents to actively harness and reconstruct past experiences based on the present context. At each decision step, a unified policy model critiques and reconstructs the retrieved experience conditioned on the current state, producing context-grounded guidance before acting. This reconstructive ability emerges naturally through end-to-end training with GRPO. Experiments on ALFWorld and WebShop show that MemHarness substantially outperforms pure RL and static memory-augmented baselines, demonstrating strong robustness in out-of-distribution (OOD) scenarios. Furthermore, our analyses reveal that this reconstruction objective not only prevents negative transfer but also serves as latent guidance during training, fundamentally improving the agent's intrinsic reasoning capabilities.

Memory-augmented LLM-based agents are vulnerable to memory injection attacks: Agents may retrieve poisoned memory from attackers, which diverts their behavior from initial user intent and finally causes task failure. However, existing defense mechanisms either incur high computational cost or suffer from information redundancy in multi-turn contexts. To address these challenges, we propose Memory Intent-Aware Neural Denoising(MIND), a lightweight defense framework for memory injection attack. Our preliminary analysis reveals that benign and poisoned trajectories exhibit distinguishable relationships between the initial user intent and subsequent behavior. Building on this observation, MIND employs an intent-aware Information Bottleneck(IB) to extract compact intent--behavior representations from the initial intent and turn-level behavior. The IB preserves intent-relevant cross-turn attack signals while filtering task-irrelevant and repetitive information, and a lightweight detector identifies malicious memories from the resulting representations. As such, MIND mitigates information redundancy in multi-turn contexts while avoiding the overhead of repeated LLM auditing. Extensive experiments show that MIND reduces attack success rates while preserving task accuracy and inference efficiency. Notably, on ReAct-StrategyQA, MIND reduces mean ASR-r and ASR-a by 55.4% and 55.3%, respectively, while matching the undefended agent in average accuracy and latency.

Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations. This creates a mismatch for weaker student agents: when a student fails because it lacks task knowledge or operational strategy, its failed trajectory may not contain enough evidence to infer the missing behavior, while the teacher trajectory may be too implicit to be internalized as reusable guidance. We propose SKILL-KD, a contrastive skill distillation framework that treats skills as an explicit distillation medium between agents of different capabilities. Given a student failure and the teacher trajectory on the same task, SKILL-KD distills their actionable discrepancy into a textual skill patch, evaluates the patch by re-running the student, and iteratively refines the patch when the student still fails. To prevent repeated local updates from causing skill drift, SKILL-KD further maintains trace-linked edit histories and performs Drift-Aware Skill Consolidation, deciding whether each patch should add a new rule, delete or modify an existing rule, or be skipped. Across five agent benchmarks and two student settings, SKILL-KD consistently improves frozen student agents over fixed-model adaptation baselines.

Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents. However, existing methods predominantly rely on sparse task rewards for policy optimization, failing to fully exploit another class of inherently dense supervisory signals naturally present during online interaction: environmental feedback following action execution. Recent theoretical studies suggest that generalization in multi-step, goal-oriented tasks hinges on predictive knowledge of environmental consequences. Inspired by this, we propose TAPO: Transition-Aware Policy Optimization for LLM Agents, a unified training framework that alternates between policy optimization and transition supervision. Beyond standard RL updates, TAPO repurposes rollout data to apply action-conditioned next-observation prediction supervision on a shared backbone model. This approach enhances the model's sensitivity to environmental transition dynamics and action consequences while concurrently optimizing the policy. It serves as a computationally lightweight, plug-and-play enhancement module for existing agent RL algorithms, requiring no additional expert data, extra sampling costs, or inference-time overhead. We conduct systematic experiments on WebShop and ALFWorld, integrating foundation models of various scales with different policy optimization algorithms. Empirical results demonstrate that TAPO consistently improves task performance over pure policy optimization baselines.

Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference time. On-policy self-distillation (OPSD) offers a promising direction, but many existing methods typically supervise students by scoring actions along student-generated trajectories. Such supervision has two limitations: teacher preferences are not validated by environment outcomes, and action-level scores underuse information from student rollouts, teacher rollouts, and their behavioral relationship. We therefore advocate outcome-verified teacher supervision and comparative learning over teacher-student trajectories. Based on this view, we propose Outcome-Verified Comparative Self-Distillation (OVCSD). OVCSD organizes failed student rollouts into a prefix tree, adaptively invokes a skill-conditioned teacher from student-reached states, and retains only outcome-verified successful continuations. It then applies localized comparative learning at the first state-aligned divergence and distills the post-divergence teacher suffix to transfer completion behavior. Experiments on ALFWorld and WebShop across three model scales show that OVCSD consistently outperforms skill-free RL and existing self-distillation baselines, achieving up to 29.7 and 5.4 absolute success-rate gains over the strongest baselines on ALFWorld and WebShop, respectively, while adding less than 3% privileged interaction during training.

Large language model (LLM) agents optimize the power, performance, and area (PPA) of register-transfer-level (RTL) designs by iterating over edits, synthesis, and PPA analysis, paying a dollar cost for every LLM call. Prior agents report the quality reached without its normalized cost, attribute that quality to an engineered cross-design memory, and hold the reasoning effort of every call fixed. We propose Ares with three corresponding innovations. (1) We introduce a normalized dollar cost per LLM call reported alongside the figure of merit (FoM), enabling fair comparison across effort levels and optimizers. (2) Using this accounting, we find the construction of the long-term memory matters little. An engineered memory brings no dependable gain over a plain concatenation of the same experience. (3) We instead adapt the per-call reasoning effort by escalating to deeper reasoning only once progress at a lower effort stalls, via a patience counter fit on 21 training designs, allocating reasoning where it pays rather than uniformly across all iterations. On three test designs unseen during training, the effort policy lowers the FoM by 23-27% where the best fixed effort reaches 16-23%, at equal normalized cost. Ares closes up to 83% of the gap from an LLM-drafted multiply-accumulate unit to its highly hand-optimized counterpart, and reaches a 25% deeper FoM than state-of-the-art Dr. RTL at 12% of its tokens.

Persistent memory lets long-running large language model agents reuse information across sessions and tasks. Yet errors in writable memory can persist and corrupt future behavior. Existing systems improve storage and retrieval, but they do not provide a transaction boundary for reliable updates and recovery. We therefore propose MemTxn, a governance layer outside the answer model. MemTxn verifies whether an update is supported by its source. It also selects the visible version when facts conflict and restores the application-visible state after a fault. The system uses Ordered PatchTest to validate writes, a Temporal Resolver to select versions, and a durable snapshot journal to recover state. On an item-disjoint audit, MemTxn accepts all 60 supported originals and rejects all 179 hard negatives. Under persistent multi-key faults on LongMemEval-S and LoCoMo states, it restores the complete declared active map without knowing the actual physical write set. On MemoryAgentBench FactConsolidation, MemTxn achieves the highest average F1 across all twelve answer-model configurations. It outperforms Dense by 17.06--24.07 points in five representative settings.

Large Language Model~(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks. However, they often struggle with long-horizon interactive tasks common in domains, such as embodied AI. The complexity and vast action spaces in these settings lead to compounding errors, where a single suboptimal action can derail an entire trajectory, causing the agent to exhaust its limited step budget on inefficient or unrecoverable paths. To overcome this without costly fine-tuning, we draw inspiration from software debugging, where execution logs are analyzed to preemptively catch errors. We propose \textit{Trajectory Graph Copilot}, a novel framework that acts as a ``copilot'' for LLM agents by diagnosing potential action errors before they are executed. At its core,\textit{Graph Debugger} models historical trajectories as a probabilistic graph and uses a Graph Neural Network to identify sequential action patterns that frequently lead to failure. Functioning as a proactive diagnostic sandbox, our method provides early warnings on potentially flawed actions, prompting the agent to self-correct. This pre-action error diagnosis prevents costly mistakes, significantly enhancing the agent's ability to complete long-horizon tasks successfully. The extensive experiments on four benchmarks with three LLM agents demonstrate a $14.69\%$ pass ratio improvement on average.

Agent self-evolution has primarily focused on learning how to act, while overlooking an equally important capability: learning to discover what an agent does not know. Existing approaches typically assume that failure discovery is given, focusing on how to repair failures once they are identified. We ask whether blind-spot diagnosis itself can be learned. We thus study diagnosis as an agent capability separate from execution, and exclude two alternative sources of progress: executor adaptation and human supervision. Under these constraints, performance cannot improve through executor updates or annotated examples, forcing all improvements to originate from the learned diagnostic capability. We propose SkillMentor, which trains a Mentor policy via reinforcement learning to generate diagnostic tasks, identify recurrent failure modes, and curate them into reusable corrective skills. Across AppWorld and BFCLv3, SkillMentor improves executor performance by an average of 44.2%. These results suggest that blind-spot diagnosis is a learnable capability, enabling self-evolution without updating executor weights or relying on human-curated data.

Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An important feature of the benchmark is that each task is paired with two economic signals: human labor time and task price proxy. These signals enable direct comparisons between human costs and LLM inference costs, as well as value-weighted evaluation. To support stable evaluation, we develop code-based verifiers from fine-grained rubrics. We evaluate several frontier LLMs together with a human baseline. Although all evaluated LLMs are substantially cheaper and faster than human workers, they have not yet approached human-level deliverable quality. The code and dataset are fully open-sourced, and more information is available on our project website: https://omegause-officeval.github.io.

As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and privacy exposure. Routers and retrievers can rank candidate tools by relevance, but a ranking alone does not determine how many are worth selecting. Existing approaches leave acquisition under heterogeneous costs unaddressed. We formulate this decision as cost-aware marginal decision-focused stopping (CAM-DF) over ranked tool prefixes, with CAM-DF-lite as a compact interpretable variant. We train directly on the offline gap between stopping now and the best continuation: its sign labels the decision, its magnitude weights each error by the payoff at stake. We prove this objective is Bayes-aligned with the stopping target and that score-only rules are suboptimal under heterogeneous costs. We evaluate on 1,343 tasks across five tool-use domains. On $τ$-bench Retail, CAM-DF attains the highest payoff among deployable methods, with gains over a predict-then-threshold baseline across all five ranking sources and two cost regimes. Our approach is state-of-the-art under heterogeneous costs and high cost pressure, with larger gains under weaker rankings. In live execution, CAM-DF exposes the agent to 37% fewer tools than full access while maintaining comparable task success. The CAM-DF family is a lightweight pre-execution plugin that turns existing tool rankings into lower-cost acquisition decisions without fine-tuning the underlying LLM.

Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once - every flight, hotel, and attraction must exist and be bookable, the days must be physically traversable, the total must clear a budget, and the plan must serve a traveler whose needs are only partly stated. Existing agent benchmarks reward these properties one at a time and grade the final output with soft or LLM-judged rubrics, which cannot certify that a returned plan is executable and are neither reproducible nor auditable. We introduce TREK (Travel Reasoning and Evaluation Kit), a benchmark for feasible itinerary synthesis: producing a single plan that is jointly constraint-correct, hallucination-free, spatio-temporally executable, budget-valid, and responsive to the traveler's unstated persona needs. TREK comprises 800 multi-constraint tasks - 533 feasible and 267 provably infeasible with typed route/entity/budget causes - over a synthetic, internally consistent knowledge base of 212,530 records across 375 cities and 13 personas, served through a production-style tool sandbox of validated RESTful APIs. Every task is scored by a fully deterministic, rule-based evaluator with no LLM judge and ships a human-verified gold reference that scores a perfect 1.0 under that same evaluator, so the ceiling is demonstrably achievable and every remaining gap is an agent limitation rather than scorer strictness. Evaluating 15 LLM agents across nine constraint dimensions, we find that even the strongest (GPT-5.6) produces a fully-feasible plan on only 46.2% of solvable tasks, with a median of 6.6% and a floor of 0.0%; satisfying travelers' unstated needs emerges as the universal bottleneck, unsolved even at the frontier. We release the dataset, tool sandbox, deterministic evaluator, and agent code as a fully reproducible benchmark.

Automatically generating cinematically expressive camera trajectories through 3D scenes from natural language descriptions is a challenging task of high practical value, with applications ranging from real-estate advertising to virtual tour creation. Existing methods either lack true 3D spatial awareness by relying on 2D image priors, or treat trajectory generation as a geometric path planning problem divorced from cinematographic semantics. We present CinemaTraj, a framework that reframes camera trajectory planning as a language-grounded spatial reasoning problem. Given a set of RGB-D images and a user prompt, CinemaTraj equips an LLM agent with a structured 3D scene graph: the agent decomposes the prompt into a sequence of atomic cinematographic movements (dolly, orbit, crane, pan, tilt, zoom, arc). Each movement is instantiated via a novel parametric trajectory representation that is both cinematographically expressive and optimizable for collision avoidance. The scene graph acts as a structured spatial prior, grounding the agent's reasoning in accurate geometric and semantic knowledge of the environment. CinemaTraj further generates synchronized voiceover and subtitles aligned with camera motion, producing narrated cinematic video outputs. We evaluate CinemaTraj on real-world ScanNet++ environments, and show that it produces prompt-faithful, collision-free trajectories with high cinematographic quality, outperforming existing approaches on prompt alignment, trajectory quality, and safety metrics.

LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control of physical AI systems. Yet, when deployed at the edge, they must tightly manage their reasoning budget while remaining reliable and deferring to a cloud-side model only when local uncertainty is too high to act safely. We propose Think Short, Defer Smart (TSDS), a framework that synergistically integrates a lightweight convergence probe, which halts on-device reasoning once the intended action has stabilized, with a perplexity-based deferral rule that escalates uncertain actions to a cloud-side model. Both mechanisms are jointly calibrated on end-to-end episode trajectories via a multi-objective Learn-Then-Test (LTT) procedure, providing simultaneous finite-sample guarantees on expected episode reward and cloud-call rate. We evaluate TSDS on four ReAct benchmarks spanning arithmetic reasoning (GSM8K), multi-hop question answering (HotpotQA), code generation (MBPP), and multi-step embodied planning (household robot), and compare against thought-calibration-only and calibrated-deferral-only standalone baselines. TSDS reduces per-episode thinking compute by 43%-73% over deferral-only baselines across HotpotQA, MBPP, and the household robot task, while maintaining certified reward and cloud-call rate guarantees.

Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling agents, where it now matters most. On $τ^2$-bench, across two open-weight model families in dense and MoE variants and two domains (eight cells, 456 episodes each, at 16-, 8-, and 4-bit weights), quantization indeed looks free on the standard metric. No cell shows a score change that survives multiple-comparison correction, and in the cell that carries the largest process damage, equivalence testing bounds the change within $\pm$7.5 points. The process tells a different story. Quantization amplifies the failure the model already exhibits at full precision (tool-name hallucination in telecom, with the same directional trend in retail entity errors) by up to 2.5$\times$ in volume (+17.6 points per task), while creating essentially no new failures. The failure set is the same at every precision (rank correlation $\geq$ 0.94, 0.18% novel events). The score stays flat because the benchmark's ten-error budget absorbs the extra failures. Shrinking the budget to two errors re-exposes a score gap of 17 points, and it does so only in the one cell where quantization added error volume, exactly as the masking account predicts. A targeted error-repair prompt, run for five telecom models at every precision, removes the damage exactly and only where it lives. Both diagnostics, the per-channel error rate and success under a shrinking budget, come from logs benchmarks already collect; we suggest reporting them alongside task reward.

Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities. However, existing cybersecurity benchmarks focus on pre-compromise settings where agents are placed in a clean and idealized environment before an attack occurs. This leaves the post-compromise setting underexplored. To address this gap, we introduce SecRespond, the first benchmark for evaluating LLM agents on the post-compromise incident-response workflow. Given a forensic disk snapshot of a compromised host together with the alerts, vulnerability scans, and baseline checks reported by a host security product, agents are required to produce forensic reports on intrusions, baseline risks, and vulnerability risks, together with a remediation plan. We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host, spanning 4 entry-point types, 21 ATT&CK techniques, and 5 operating systems. We evaluate 23 frontier LLMs on the OpenCode agent harness. Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions and to produce comprehensive, verified remediation plans, with no model achieving complete detection and remediation on any single range. This reveals a fundamental bottleneck in building agents for real-world incident response. The benchmark is publicly available at https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond.

Large language model agents often encounter related yet distinct tasks that share reusable solution patterns. Yet standard agentic reinforcement learning treats tasks as independent episodes, while existing approaches to skill learning either focus on repeated attempts of one task or use pipelines with multiple stages that entangle extraction, retrieval, and execution. We introduce SkillRise, a unified reinforcement learning framework for learning skills across tasks. SkillRise organizes related instances into progressively challenging sequences and uses a single policy to alternate between task solving and curating an evolving skill document passed directly to the next task. Decoupled credit assignment across tasks supervises solving with the current task outcome and curation with discounted downstream outcomes. Experiments on ALFWorld, WebShop, and ScienceWorld show that SkillRise achieves the strongest Pass@1 performance among the compared methods, with gains over the strongest baseline ranging from 2.3 to 8.5 percentage points. Although trained across distinct tasks, its learned curation policy remains effective for repeated attempts on the same task. Further analysis reveals scaling at test time across tasks: performance improves with longer sequences of related tasks even when each task is attempted only once. This trend suggests that SkillRise reuses transferable skills across tasks rather than benefiting from repeated sampling of the same task. SkillRise further retains strong performance while substantially reducing the runtime overhead of skill learning pipelines with multiple stages. Together, these results provide a simple and efficient training paradigm for LLM agents to extract, refine, and reuse transferable skills across tasks.

Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A promising solution is to treat skills as trainable states and optimize them in the same way as model parameters in neural network training. However, data-driven skill optimization is prone to overfitting to the limited trajectories collected from real environments. Overexploiting these trajectories overfits the current batch, while unconstrained exploration causes regression on previously solved cases. This tension motivates a constrained search view of skill self-evolution, governed by an exploration--exploitation trade-off. We propose SkillBoost, a three-stage framework that mitigates both risks: structured exploitation localizes observed failures to editable skill components, prior-guided exploration draws on prior knowledge in the LLM to generate diverse repair candidates, and verified acceptance commits a candidate only when it improves performance within a regression bound. Experiments across 23 model--benchmark configurations show that SkillBoost achieves state-of-the-art performance while mitigating overfitting, outperforming both human-crafted and LLM-generated skills. Transfer experiments further show that optimized skills can be reused by other agents on similar tasks.

Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools. Yet research has largely passed over this medium: prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested: that an agent can keep a growing store organized as memories accumulate, conflict, and go stale, and that this organization pays. We present the first systematic exploration of filesystem-based memory for LLM agents. We formalize the setting as three roles around one memory filesystem: a management agent integrates and organizes incoming content, a search agent answers queries with cited sources, and an execution agent supplies task trajectories that are distilled into skills, unifying declarative memory and skills in a single store. Across long-conversation benchmarks and embodied tasks, we vary memory shape (agent-organized hierarchy, verbatim dump, chunk retrieval), stream scale, tool harness (sandboxed shell, memory-tool-style functions, varied search tooling), and the strengths of the management and search agents, tracking answer quality, cost, and store health as memory grows. What organization reliably buys is search economy: organized stores roughly halve retrieval cost where material is large. Today's agents, however, fall short of the default's promise: in our growth study, organization erodes for all but the strongest management agent, and no agent we measure converts organization itself into better answers. And the model is not the only lever over a store's shape: changing the tool set alone reshapes the store as strongly as swapping the model. The study turns the filesystem default from an assumption into a design space for agent memory.

As LLM agents move from decision support to autonomous procurement, firms need to know whether delegated negotiators create value, divide it predictably, and avoid money-losing contracts. We study this in a canonical supply chain bargaining problem: a buyer with private demand information negotiates a quantity-payment contract with an uninformed seller. We benchmark nine LLMs from OpenAI, Google, and Alibaba against a validated Perfect Bayesian Equilibrium across 9,840 LLM-to-LLM negotiations. First, capability governs value creation. Agents agree in 98.9% of negotiations and capture 95.4% of first-best surplus undiscounted, but average 2.98 rounds against the benchmark's 1.25, and this delay erodes 21-34% of surplus. Capability also governs reliability: baseline models accept individually irrational contracts in 19.2% of cases, versus 0.0-0.6% at mid-tier and flagship, making automated profit verification the binding guardrail below that threshold. Second, surplus capture is relational. Provider identity predicts who captures surplus better than capability rank: self-play buyer shares average 40% for OpenAI, 50% for Google, and 70% for Alibaba's Qwen, an ordering that survives restricted communication and no discounting. Reversing which provider sells moves the division by 7-18 percentage points, and the capable Qwen flagship is the weakest cross-family seller: vendor choice is a first-order distributional decision. Third, the prompt is a strategic lever. Delegation separates the principal's economic patience from the agent's prompted strategic patience, a free deployment choice that is the single strongest driver of surplus division (90% of explained variance). Together these establish an equilibrium-referenced audit of AI agents along three dimensions: discounted efficiency, distributional profile, and operational reliability.

Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and learning from checkpoint feedback. Can LLM agents automate this loop? Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation, obscuring agents' research capability. We introduce RSIBench-Data, a controlled benchmark of LLM agents as data-centric researchers with a fixed post-training stack. Agents iteratively revise training-data strategies for a fixed target model; training and serving use Tinker-backed services, official evaluation runs through Harbor and E2B sandboxes, and budgets are fixed across agents. We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics. Agents demonstrate core data-centric research capabilities: in 58.33% of settings, they improve upon the first valid attempt by refining strategies from feedback. However, improvement is inconsistent. Among searches continuing after the best observed score, 78.26% end with a lower-scoring final attempt, while the rest only recover the same peak. A strong candidate may therefore appear early or midway through a run even as later revisions fail. Trajectory analysis identifies four patterns in stronger runs: accurate hypotheses, validation-grounded supervision, behavior-aligned data, and preservation of strong checkpoints. These findings suggest that current agents can make useful data-centric discoveries but cannot yet translate feedback into consistent improvements. RSIBench-Data provides a measurable, auditable testbed for the research capabilities required for recursive self-improvement. We open-source our code at https://github.com/evolvent-ai/RSIBench-Data.

Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks. However, existing trajectory-to-skill methods often produce flat collections of high-level textual skills that are stored and retrieved independently, leaving skill relations underutilized and maintaining a gap between high-level skills and executable actions. In this paper, we propose HiSkill, a hierarchical skill graph framework that organizes interaction trajectories into a directed graph with skill nodes, AtomicOp nodes, and typed edges. Specifically, the graph connects reusable high-level skills with executable action templates, while also capturing decomposition, temporal transition, compatibility, support, and recovery relations among them. At inference time, HiSkill retrieves a compact task-relevant subgraph and performs subgraph-guided task execution, where a symbolic task state, an active skill, and the retrieved subgraph guide the LLM agent to switch skills, select AtomicOps, and ground executable actions iteratively. Experiments on three interactive environments show that HiSkill outperforms state-of-the-art baselines while reducing inference token consumption, demonstrating the effectiveness of bridging high-level skills and executable action grounding through a hierarchical skill graph. Our data and code is available at https://github.com/BUPT-GAMMA/HiSkill.

Agent harnesses have become the operational infrastructure of modern large language model agents, coordinating context, tools, verification, and execution control to translate latent model capability into reliable long-horizon behavior. However, reliable long-horizon behavior requires harness control to adapt to task demands, execution environments, and evolving execution states, whereas current harnesses predominantly rely on hand-crafted or globally fixed policies; this mismatch manifests as unnecessary computational overhead and, in adverse cases, reduced task success. To address this limitation, we formulate the task of enabling adaptive orchestration in harness systems as a causal learning problem and propose Counterfactual Harness Intervention Learning for Long-Horizon Agents (CHILL-Harness). CHILL-Harness intervenes at the orchestration layer to enable advantage-guided workflow adaptation, thereby improving reasoning and execution efficiency while preserving task performance. Specifically, we develop causal intervention effect learning as the effect-estimation component of CHILL-Harness to estimate intervention-relative workflow advantage from confidence-weighted execution evidence and identify advantageous workflow adaptations. We further introduce advantage-realizing causal orchestration as its realization component to adaptively allocate counterfactual reasoning and realize only workflow adjustments supported by sufficient expected advantage. Finally, we incorporate a success-preserving objective and advantage-margin authorization constraints into CHILL-Harness to promote reliable adaptation. Extensive experiments on heterogeneous long-horizon tasks spanning information seeking, software engineering, and terminal interaction show that CHILL-Harness consistently preserves or improves task success while substantially reducing token consumption and execution time.

Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predicting and pre-executing an agent's next tool call if the prediction matches the agent's eventual tool call, but existing speculators are typically separate draft models or cached traces that are poorly aligned with the deployed agent's own behavior. We identify this speculator-agent gap and show that the target agent itself is a strong next-call speculator. This points to a simpler design: unifying the agent and speculator within the same model. In this paper, we introduce the self-speculating agent, a single model that both solves tasks in agent mode and predicts its next tool call from partial trajectories in speculator mode, fully reusing prefix KV cache. To enable this dual-mode agent without degrading performance, we propose a joint agent-speculator reinforcement learning method, which derives speculation targets from the agent's own rollouts and alternates agent and speculator updates. Across agentic search QA and conversational tool-use agentic tasks, our method improves average next tool-call Hit@1 from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, while preserving agent task success.

Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small task-relevant subset from a library of thousands of tools before the agent acts, has therefore become a critical component of LLM agent pipelines. However, existing retrievers either score each tool in isolation or assemble the tool set sequentially, so the joint utility of a candidate set is never evaluated as a whole. In this paper, we propose HYSET, short for HYperedge-based SEt-level Tool retrieval. Our contributions are threefold: (i) we formulate tool retrieval as query-conditioned hyperedge prediction on a tool co-invocation hypergraph, under which the tool set itself becomes the unit of scoring and most existing retrieval paradigms reduce to restricted instances; (ii) we capture size-dependent tool compatibility through cardinality-specific interactions; and (iii) we design HYSET as a pre-selection module requiring no modification to the downstream agent. Experiments on ToolBench demonstrate that HYSET consistently outperforms state-of-the-art baselines in both tool retrieval performance and end-to-end task success. Beyond the in-domain setting, HYSET further supports zero-shot/few-shot transfer, generalizing to held-out tools/categories and unseen domains with minimal supervision.

Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a planning strategy, and a verification policy. Two 2026 systems, Meta-Harness (Lee et al., 2026) and HyperAgents (Meta AI, 2026), show that this harness can itself be optimized or even self-rewritten by an agentic proposer -- at the cost of either an expensive code-search loop or unconstrained self-modifying code, neither of which is auditable or usable with a fully black-box model API. We take a narrower, more constrained position: treat the harness as a small, fixed, human-legible action space and learn a policy over it online with classic sample-efficient reinforcement learning (an $ε$-greedy contextual bandit and REINFORCE), scored against a multi-objective reward (task success, verifier score, policy compliance, cost, latency, and an unsupported-claim penalty). We instantiate this control system with DSPy (Khattab et al., 2024) as both the context assembler and the source of the strongest non-adaptive baseline (a DSPy BootstrapFewShot static prompt), and evaluate it across three verifiable task domains -- tool-use workflows, code generation (HumanEval), and multi-hop retrieval QA (HotpotQA) -- and two model providers (a local Ollama model and AWS Bedrock). We release the harness-control-system code, the cross-domain verifiable task suite, the full trajectory/reward-decomposition logs from training, and a provider-agnostic deployment recipe for applying this to a new organization's domain and verification setup.

Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR) relies on sparse final rewards that reveal little about which decisions determine success. Denser process signals could supply this missing turn-level credit, but existing sources are hard to keep both cheap and accurate. We observe that changes in a game solver's state value reveal whether an action advances the state toward success. Building on this insight, we propose CAST (Credit Assignment from Solver Teachers), which converts these value changes into solver advantages and injects them into RLVR as turn-level signals. We further show that, under a soft-optimal solver assumption, maximizing the solver advantage is equivalent to on-policy distillation from the solver, requiring only scalar values rather than teacher logits. Across Sokoban, Minesweeper, and Rush Hour, CAST outperforms all trained baselines on every game under both in-domain and unseen-difficulty evaluation and achieves the highest average zero-shot performance on ALFWorld and WebShop. Our code is available at https://github.com/Wloner0809/CAST.

The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactions between LLM agents and external environments, Model Context Protocol (MCP) tools have emerged as a de facto standard and have been widely integrated into these systems. However, the use of MCP tools also introduces new safety risks, as LLM agents can be induced to perform malicious or unauthorized actions. Although prior work has proposed defenses for securing tool use in LLM agents, most methods rely on static analysis, i.e., inspecting prompts and generated outputs, which limits the defense effectiveness and robustness. To address these limitations, we propose MTGuard, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis. Extensive evaluation demonstrates that MTGuard effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user tasks.

Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold: plausible changes are accepted as progress while real-world outcomes stagnate or regress. We name this failure mode the progress mirage and show, with controlled measurement, that it is a question of what the evaluator is grounded in. We built a testbed that holds the agent and its tool surface fixed and manipulates only the information-channel type of the evaluator that gates the loop. A world-state oracle, unfakeable in principle, is enforced by container and network isolation and verified at every run. Across 54 cycles a frontier agent claimed improvement every time, yet 56 percent had a measured delta of zero or below. Self-report was thus uninformative, and the self-verdict gate degenerated into accept-all, eroding the best deployed state it had reached by 19 percent. Even the strongest in-band judge, reading the full artifact text, the change diff, and its own verdict history, accepted cycles of which 44 percent were real-world regressions and rejected 38 percent of real improvements; the preregistered adversarial hypothesis that a strong judge closes the gap was rejected. On a boundary task whose success specification is verifiable from the artifact itself, the same judge's mirage vanished to zero and the gap collapsed within the registered threshold, showing that the gap depends on where the success signal resides. A sign-only variant returning only the acceptance verdict kept real-world output similar to full feedback (110.0 versus 113.0), locating the benefit in the gate's grounding rather than in feedback content. For open-ended objectives whose success signal lives outside the transcript, scaling up the judge is not enough; out-of-band evaluation with real-world access is a structural requirement.

This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and appraise one another. Each agent perceives its neighbors through visual, auditory, and tactile channels, then appraises these perceptions in light of its prompted personality profile, memory, current affective state, and situational context. Appraisal is carried out by an LLM, which updates the agent's internal affective state and selects its outward expression. The architecture contains no hand-authored mechanism for directly transferring affective state between agents; instead, inter-agent influence arises through the perception-appraisal-expression loop. The agent representation draws on the Big Five personality model and Russell's circumplex model of affect. To limit latency, low-level steering and navigation are handled by a conventional crowd simulator operating independently of the LLM-based cognitive layer. We evaluate the architecture across five scenario environments spanning alarming, joyful, and neutral situations in different spatial layouts. The results show that the system produces emotional contagion dynamics with spatial, temporal, and personality-dependent structure in sparse, small crowds. Alarm spreads from seeded agents as a traveling front, the mean alarmed fraction settles at a nonzero plateau, and the distribution of prompted personality profiles determines whether an ambiguous alarm ignites panic and whether a provocation is interpreted as anger or fear. We further evaluate the appraisal step through controlled experiments across prompt variants, sampling temperatures, and four model backends, showing that the dynamics are backend-dependent.

The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated. In the State-of-the-Art (SOTA) research, fifteen (model, corpus) configurations were trained using Proximal Policy Optimization (PPO). The experiments included Pythia-70M, 160M, 410M and SmolLM2-135M, 360M on the TinyStories, CNN/DailyMail, and Wikitext-103 corpora. Three reproducible failure modes were identified in small-scale language models: silent LoRA parameter freezing in standard PEFT/TRL pipelines, numerical overflow in importance ratios when using bfloat16, and catastrophic policy collapse due to reward-model error. These issues were addressed using a merge-and-reinitialize adapter technique, float32 precision during PPO updates, and a three-layer safety mechanism comprising reward whitening, importance-ratio guarding, and weight rollback. In this paper, a capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model ($\text{PPL}<20$) and a discriminative reward signal, rather than on the number of model parameters. The proposed system converged stably in all experiments and improved preference win rate over the SFT baseline in configurations with a fluent prior and an informative reward signal. Furthermore, it outperformed instruction-tuned baselines while requiring significantly less training data. All checkpoints, preference datasets, and training scripts are publicly released$^§$.